# US 12,014,736 B2 · Information processing apparatus and information processing method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,014,736 B2 - Document ID: US12014736B2 - Status: Granted - Kind: B2 - Application number: 17/413,158 - Filed: 2019-10-30 - Published: 2022-02-17 - Granted: 2024-06-18 - Earliest claimed: 2018-12-19 - Assignees: Sony Group Corporation - Applicants: Sony Group Corporation - Inventors: Tatsuma Sakurai; Ichitaro Kohara - Web page: https://patentgrep.com/patent/US12014736B2 ## CPC - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - A63H 5/00: Musical or noise- producing devices for additional toy effects other than acoustical (musical tops A63H1/28; {sound-producing dolls A63H3/28; musical toy vehicles A63H17/268; acoustical vehicle-signalling devices A63H17/32; whistling toy locomotive arrangements A63H19/14}; music, sound or noise production in general G10) - A63H 11/00: Self-movable toy figures - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G10L 15/28: Constructional details of speech recognition systems - A63H 2200/00: Computerized interactive toys, e.g. dolls - G10L 2015/223: {Execution procedure of a spoken command} - G10L 2015/226: {using non-speech characteristics} - G10L 2015/227: {of the speaker; Human-factor methodology} - G10L 2015/228: {of application context} - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - A63H: TOYS, e.g. TOPS, DOLLS, HOOPS OR BUILDING BLOCKS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract An information processing apparatus that includes a control unit controlling an action of an autonomous operation unit, and in which the control unit controls transition of plural states relating to speech recognition processing through the autonomous operation unit based on a detected trigger, and the states include a first active state in which an action of the autonomous operation unit is restricted, and a second active state in which the speech recognition processing is performed. An information processing method in which a processor controls an action of an autonomous operation unit, the controlling includes controlling transition of plural states relating to speech recognition processing through the autonomous operation unit based on a detected trigger, and the states include a first active state in which an action of the autonomous operation unit is restricted, and a second active state in which the speech recognition processing is performed. ## Claims ### Claim 1 An information processing apparatus, comprising: circuitry configured to: control an action of an autonomous operation unit; control a transition between a plurality of states related to a speech recognition process through the autonomous operation unit, wherein the plurality of states includes a first active state in which the action of the autonomous operation unit is restricted, and a second active state in which the speech recognition process is performed; accumulate speech sound collected by the autonomous operation unit in the first active state; control the transition from the first active state to the second active state based on a detection of a trigger; and control, in the second active state, transmission of the speech sound accumulated prior to the detection of the trigger to a speech recognition apparatus. ### Claim 2 (depends on 1) The information processing apparatus according to claim 1, wherein the plurality of states further includes a normal state in which the action of the autonomous operation unit is not restricted. ### Claim 3 (depends on 2) The information processing apparatus according to claim 2, wherein the circuitry is further configured to control the action of the autonomous operation unit such that a volume of an operating noise is lower than a threshold in the first active state. ### Claim 4 (depends on 1) The information processing apparatus according to claim 1, wherein the circuitry is further configured to: cause the autonomous operation unit to transition to the second active state in a case where a postfix trigger indicating an intention of a posterior inquiry with respect to the autonomous operation unit is detected after a speech of a user has started in the first active state; and control the transmission of the speech sound accumulated before detection of the postfix trigger to the speech recognition apparatus. ### Claim 5 (depends on 4) The information processing apparatus according to claim 4, wherein the postfix trigger includes at least one of detection of a specific word, detection of a specific gesture, detection of a touch to the autonomous operation unit, detection of a face of the user, detection of a sudden sound, and detection of a moving body. ### Claim 6 (depends on 1) The information processing apparatus according to claim 1, wherein the circuitry is further configured to: cause the autonomous operation unit to make an active speech and behavior to a user in the first active state; and cause the autonomous operation unit to transition to the second active state based on a reaction of the user to the active speech and behavior. ### Claim 7 (depends on 1) The information processing apparatus according to claim 1, wherein the circuitry is further configured to: cause the autonomous operation unit to transition to the second active state in a case where a prefix trigger indicating an intention of anterior inquiry with respect to the autonomous operation unit is detected before start of a speech of a user in the first active state; and control transmission of the speech sound collected after detection of the prefix trigger to the speech recognition apparatus. ### Claim 8 (depends on 2) The information processing apparatus according to claim 2, wherein the circuitry is further configured to cause the autonomous operation unit to transition to the first active state in a case where an environmental trigger indicating that a possibility of a user making a speech with respect to the autonomous operation unit has become high in the normal state. ### Claim 9 (depends on 8) The information processing apparatus according to claim 8, wherein the environmental trigger includes at least one of detection of a touch to the autonomous operation unit, detection of a change of illumination, detection of a moving body, and detection of a sudden sound. ### Claim 10 (depends on 2) The information processing apparatus according to claim 2, wherein the circuitry is further configured to cause the autonomous operation unit to transition to the normal state in a case where an end environmental trigger indicating that a possibility of a user making a speech with respect to the autonomous operation unit has become low is detected in the first active state. ### Claim 11 (depends on 10) The information processing apparatus according to claim 10, wherein the end environmental trigger includes at least one of detection of an end of touch to the autonomous operation unit, detection of decrease of illumination, and detection of decrease of an environmental sound. ### Claim 12 (depends on 2) The information processing apparatus according to claim 2, wherein the circuitry is further configured to cause the autonomous operation unit to transition to one of the first active state or the normal state in a case where a conversation end trigger related to an end of a conversation is detected in the second active state. ### Claim 13 (depends on 12) The information processing apparatus according to claim 12, wherein the conversation end trigger includes at least one of detection of a specific word, detection of a specific gesture, detection of a touch to the autonomous operation unit, end of detection of a face of a user, and detection of a sudden sound. ### Claim 14 (depends on 2) The information processing apparatus according to claim 2, wherein the circuitry is further configured to cause the autonomous operation unit to make different expressions in the normal state, the first active state, and the second active state. ### Claim 15 (depends on 1) The information processing apparatus according to claim 1, wherein the information processing apparatus includes the autonomous operation unit. ### Claim 16 An information processing method, comprising: controlling an action of an autonomous operation unit; controlling a transition between a plurality of states related to a speech recognition process through the autonomous operation unit based on a detected trigger, wherein the plurality of states includes a first active state in which the action of the autonomous operation unit is restricted, and a second active state in which the speech recognition process is performed; accumulating speech sound collected by the autonomous operation unit in the first active state; controlling the transition from the first active state to the second active state based on a detection of a trigger; and controlling, in the second active state, transmission of the speech sound accumulated prior to the detection of the trigger to a speech recognition apparatus. ### Claim 17 A non-transitory computer-readable medium having stored thereon, computer-executable instructions which, when executed by a processor of an information processing apparatus, cause the processor to execute operations, the operations comprising: controlling an action of an autonomous operation unit; controlling a transition between a plurality of states related to a speech recognition process through the autonomous operation unit, wherein the plurality of states includes a first active state in which the action of the autonomous operation unit is restricted; and a second active state in which the speech recognition process is performed; accumulating speech sound collected by the autonomous operation unit in the first active state; controlling the transition from the first active state to the second active state based on a detection of a trigger; and controlling, in the second active state, transmission of the speech sound accumulated prior to the detection of the trigger to a speech recognition apparatus. ### Claim 18 An information processing apparatus, comprising: circuitry configured to: control an action of an autonomous operation unit; control transition between a plurality of states related to a speech recognition process through the autonomous operation unit, wherein the plurality of states includes a first active state in which the action of the autonomous operation unit is restricted, a second active state in which the speech recognition process is performed, and a normal state in which the action of the autonomous operation unit is not restricted; and cause the autonomous operation unit to transition to one of the first active state or the normal state in a case where a conversation end trigger related to an end of a conversation is detected in the second active state.